Parallel Probabilistic Neural Network ( PPNN ) 1 Parallel Probabilistic Neural Network ( PPNN )

---It was pointed out in this paper that the planar topology of current backpropagation neural network (BPNN) sets limits to solve the slow convergence rate problem, local minima, incapability of learning etc. problems associated with BPNN. The parallel probabilistic neural network (PPNN) using a new neural network topology---stereotopology----was proposed to overcome these problems. The learning ability and the generalization ability of BPNN and PPNN were compared for several problems. The simulation results show that PPNN was capable of learning any kinds of problems much faster than BPNN and generalized better than BPNN too. It was analyzed that the faster, universal learnability of PPNN was due to the parallel characteristic of PPNN’s stereotopology, and the better generalization ability came from the probabilistic characteristic of PPNN’s memory retrieval rule PMRR.